Scrape images from a search engine with JavaScript and Puppeteer

const puppeteer = require("puppeteer")const data = require("./dog-breeds.json")const script = async () => {  //this will open visibly a chromium window, this is useful to see what is going on and test stuff before the finalized script  const browser = await puppeteer.launch({ headless: false, slowMo: 100 })  const page = await browser.newPage()  //loop on every breed  for (let dogBreed of data) {    console.log("Start for breed:", dogBreed)    const url = `https://duckduckgo.com/?q=${dogBreed.replaceAll(      " ",      "+"    )}&va=b&t=hc&iar=images&iax=images&ia=images`    //in case we encounter a page without images or an error    try {      await page.goto(url)      //make sure the page is loaded and contain our targeted element      await page.waitForNavigation()      await page.waitForSelector(".tile--img__media")      await page.evaluate(        () => {          const firstImage = document.querySelector(".tile--img__media")          //we open the panel that contains the image info          firstImage.click()        },        { delay: 400 }      )      //get the link of the image from the panel      await page.waitForSelector(".detail__pane a")      const link = await page.evaluate(        () => {          const links = document.querySelectorAll(".detail__pane a")          const linkImage = Array.from(links).find((item) =>            item.innerText.includes("fichier")          )          return linkImage?.getAttribute("href")        },        { delay: 250 }      )      console.log("link succesfully retrieved:", link)      console.log("=====")    } catch (e) {      console.log(e)    }  }}script()

const stream = fs.createWriteStream(dogBreed + ".jpg")await https.get(link, async function(response) {  response.pipe(stream)  stream.on("finish", () => {    stream.close()    console.log("Download Completed")  })})//resize to a maximum width or height of 1000pxawait sharp(`./${dogBreed}.jpg`)  .resize(1000, 1000)  .toFile(`./${dogBreed}-small.jpg`)